Mu-Net:Multi-Path Upsampling Convolution Network for Medical Image Segmentation

Medical image segmentation plays an important role in clinical diagnosis,quantitative analysis,and treatment process.Since 2015,U-Net-based approaches have been widely used formedical image segmentation.The purpose of the U-Net expansive path is to map low-resolution encoder feature maps to full input resolution feature maps.However,the consecutive deconvolution and convolutional operations in the expansive path lead to the loss of some high-level information.More high-level information can make the segmentationmore accurate.In this paper,we propose MU-Net,a novel,multi-path upsampling convolution network to retain more high-level information.The MU-Net mainly consists of three parts:contracting path,skip connection,and multi-expansive paths.The proposed MU-Net architecture is evaluated based on three different medical imaging datasets.Our experiments show that MU-Net improves the segmentation performance of U-Net-based methods on different datasets.At the same time,the computational efficiency is significantly improved by reducing the number of parameters by more than half.

Point cloud upsampling generative adversarial network based on residual multi-scale off-set attention

Background Owing to the limitations of the working principle of three-dimensional(3D) scanning equipment, the point clouds obtained by 3D scanning are usually sparse and unevenly distributed. Method In this paper, we propose a new generative adversarial network(GAN) that extends PU-GAN for upsampling of point clouds. Its core architecture aims to replace the traditional self-attention(SA) module with an implicit Laplacian offset attention(OA) module and to aggregate the adjacency features using a multiscale offset attention(MSOA)module, which adaptively adjusts the receptive field to learn various structural features. Finally, residual links are added to create our residual multiscale offset attention(RMSOA) module, which utilizes multiscale structural relationships to generate finer details. Result The results of several experiments show that our method outperforms existing methods and is highly robust.

SR-AFU: super-resolution network using adaptive frequency component upsampling and multi-resolution features

Image super-resolution (SR) is one of the classic computer vision tasks. This paper proposes a super-resolution network based on adaptive frequency component upsampling, named SR-AFU. The network is composed of multiple cascaded dilated convolution residual blocks (CDCRB) to extract multi-resolution features representing image semantics, and multiple multi-size convolutional upsampling blocks (MCUB) to adaptively upsample different frequency components using CDCRB features. The paper also defines a new loss function based on the discrete wavelet transform, making the reconstructed SR images closer to human perception. Experiments on the benchmark datasets show that SR-AFU has higher peak signal to noise ratio (PSNR), significantly faster training speed and more realistic visual effects compared with the existing methods.

Efficient Computation Offloading in Mobile Cloud Computing for Video Streaming Over 5G

In this paper,we investigate video quality enhancement using computation offloading to the mobile cloud computing(MCC)environment.Our objective is to reduce the computational complexity required to covert a low-resolution video to high-resolution video while minimizing computation at the mobile client and additional communication costs.To do so,we propose an energy-efficient computation offloading framework for video streaming services in a MCC over the fifth generation(5G)cellular networks.In the proposed framework,the mobile client offloads the computational burden for the video enhancement to the cloud,which renders the side information needed to enhance video without requiring much computation by the client.The cloud detects edges from the upsampled ultra-high-resolution video(UHD)and then compresses and transmits them as side information with the original low-resolution video(e.g.,full HD).Finally,the mobile client decodes the received content and integrates the SI and original content,which produces a high-quality video.In our extensive simulation experiments,we observed that the amount of computation needed to construct a UHD video in the client is 50%-60% lower than that required to decode UHD video compressed by legacy video encoding algorithms.Moreover,the bandwidth required to transmit a full HD video and its side information is around 70% lower than that required for a normal UHD video.The subjective quality of the enhanced UHD is similar to that of the original UHD video even though the client pays lower communication costs with reduced computing power.

MsFireD-Net:A lightweight and efficient convolutional neural network for flame and smoke segmentation

With the rising frequency and severity of wildfires across the globe,researchers have been actively searching for a reliable solution for early-stage forest fire detection.In recent years,Convolutional Neural Networks(CNNs)have demonstrated outstanding performances in computer vision-based object detection tasks,including forest fire detection.Using CNNs to detect forest fires by segmenting both flame and smoke pixels not only can provide early and accurate detection but also additional information such as the size,spread,location,and movement of the fire.However,CNN-based segmentation networks are computationally demanding and can be difficult to incorporate onboard lightweight mobile platforms,such as an Uncrewed Aerial Vehicle(UAV).To address this issue,this paper has proposed a new efficient upsampling technique based on transposed convolution to make segmentation CNNs lighter.This proposed technique,named Reversed Depthwise Separable Transposed Convolution(RDSTC),achieved F1-scores of 0.78 for smoke and 0.74 for flame,outperforming U-Net networks with bilinear upsampling,transposed convolution,and CARAFE upsampling.Additionally,a Multi-signature Fire Detection Network(MsFireD-Net)has been proposed in this paper,having 93%fewer parameters and 94%fewer computations than the RDSTC U-Net.Despite being such a lightweight and efficient network,MsFireD-Net has demonstrated strong results against the other U-Net-based networks.

RealFuVSR:Feature enhanced real-world video super-resolution

Background Recurrent recovery is a common method for video super-resolution(VSR)that models the correlation between frames via hidden states.However,the application of this structure in real-world scenarios can lead to unsatisfactory artifacts.We found that in real-world VSR training,the use of unknown and complex degradation can better simulate the degradation process in the real world.Methods Based on this,we propose the RealFuVSR model,which simulates real-world degradation and mitigates artifacts caused by the VSR.Specifically,we propose a multiscale feature extraction module(MSF)module that extracts and fuses features from multiple scales,thereby facilitating the elimination of hidden state artifacts.To improve the accuracy of the hidden state alignment information,RealFuVSR uses an advanced optical flow-guided deformable convolution.Moreover,a cascaded residual upsampling module was used to eliminate noise caused by the upsampling process.Results The experiment demonstrates that RealFuVSR model can not only recover high-quality videos but also outperforms the state-of-the-art RealBasicVSR and RealESRGAN models.

Study on the off situ reconstruction of the core neutron field based on dual-task hybrid network architecture

The off situ accurate reconstruction of the core neutron field is an important step in realizing real-time reactor monitoring.The existing off situ reconstruction method of the neutron field is only applicable to cases wherein a single region changes at a specified location of the core.However,when the neutron field changes are complex,the accurate identification of the individual changed regions becomes challenging,which seriously affects the accuracy and stability of the neutron field recon-struction.Therefore,this study proposed a dual-task hybrid network architecture(DTHNet)for off situ reconstruction of the core neutron field,which trained the outermost assembly reconstruction task and the core reconstruction task jointly such that the former could assist the latter in the reconstruction of the core neutron field under core complex changes.Furthermore,to exploit the characteristics of the ex-core detection signals,this study designed a global-local feature upsampling module that efficiently distributed the ex-core detection signals to each reconstruction unit to improve the accuracy and stability of reconstruction.Reconstruction experiments were performed on the simulation datasets of the CLEAR-I reactor to verify the accuracy and stability of the proposed method.The results showed that when the location uncertainty of a single region did not exceed nine and the number of multiple changed regions did not exceed five.Further,the reconstructed ARD was within 2%,RD_(max)was maintained within 17.5%,and the number of RD≥10%was maintained within 10.Furthermore,when the noise interference of the ex-core detection signals was within±2%,although the average number of RD≥10%increased to 16,the average ARD was still within in 2%,and the average RD_(max)was within 22%.Collectively,these results show that,theoretically,the DTHNet can accurately and stably reconstruct most of the neutron field under certain complex core changes.